CN114298642A - Method for extracting urban truck trip OD from trajectory data - Google Patents

Abstract

The invention provides a method for extracting the OD of truck travel in a city from trajectory data. The method includes: determining the speed threshold of the trucks in the city, identifying the parking points from the truck trajectory according to the speed threshold; sorting the parking points of the trucks in ascending order of the parking time, and determining the multi-level time by drawing the Lorentz curve of the parking time Threshold; according to the multi-level time threshold, measure the circuitous degree of the single trip path of the truck, and extract the potential trip OD point from the truck parking point; remove the temporary parking point in the potential trip OD point, and extract the actual trip OD of the truck point. The invention proposes a dynamic identification method for the OD point of truck travel, which can be applied to all cities in the country. The method is highly transferable, low in complexity and easy to implement.

Description

A method of extracting the OD of truck trips in the city from trajectory data

technical field

The invention relates to the technical field of urban freight management, in particular to a method for extracting OD of freight vehicle travel in a city from trajectory data.

Background technique

In the urban cargo transportation system, truck transportation plays a key supporting role and is the main form of transportation between large industrial enterprises, logistics warehouses and ports. However, truck transportation can also lead to serious social and environmental problems, such as traffic accidents and air pollution, which pose challenges to the sustainable development of cities. In order to eliminate the negative externalities of urban freight and improve the efficiency of the freight system, relevant departments and organizations need to formulate feasible freight policies. Large-scale truck travel OD (Origin to Destination) information is the basic data for formulating these freight policies, providing data support for in-depth understanding of the urban freight system.

Traditionally, truck travel OD information is obtained through traffic surveys. This method is time-consuming and expensive, so the amount of data obtained is limited and insufficient for urban freight system analysis. In the era of big data, the development and application of satellite positioning technology makes it possible to obtain large-scale truck trajectory data through on-board positioning equipment. However, how to extract the OD information of truck trips from the trajectory data is a big problem in practice, and it has not been well solved. At present, there are few studies on OD extraction of truck travel, mainly including the following:

A method for extracting the OD of a truck trip in the prior art is: identifying the type of the stop point of the truck with the aid of truck driver survey data, land use data and other auxiliary information. The disadvantage of this method is that although it can achieve a good recognition effect when studying small samples, it is limited by the amount of auxiliary information, resulting in poor portability of the method.

Another method of extracting the OD of truck trips in the prior art is to use SVM (support vector machines, support vector machines) to classify and identify the parking spots of trucks based on the characteristics of the truck's stay time and the distance to the city center. The disadvantage of this method is that the actual travel OD information of trucks must be known in advance as a test set, and this information is difficult to obtain directly in practice. Not only that, the method is complex and difficult to apply to large-scale truck data.

SUMMARY OF THE INVENTION

The embodiment of the present invention provides a method for extracting the travel OD of trucks in the city from trajectory data, so as to realize the effective and dynamic identification of the travel OD of trucks.

In order to achieve the above objects, the present invention adopts the following technical solutions.

The methods of extracting the OD of truck trips in the city from trajectory data include:

determining the speed threshold of the truck in the city, and identifying the parking point from the truck trajectory according to the speed threshold;

Sort the parking points of the trucks in ascending order of the parking time, and determine the multi-level time threshold by drawing the Lorentz curve of the parking time;

According to the multi-level time threshold, the circuitous degree of the single travel path of the truck is measured, and the potential travel OD point is extracted from the parking point of the truck;

Eliminate the temporary parking points in the potential travel OD points, and extract the actual travel OD points of the delivery vehicle.

Preferably, the parking points of the trucks are sorted in ascending order of parking time, and the multi-level time threshold is determined by drawing a Lorentz curve of the parking time, including:

Calculate the average speed of two consecutive GPS points in the GPS trajectories of all trucks in the city respectively, and obtain the distribution of the average speed of all trucks. The distribution of the average speed of the truck is the mixed distribution of the data drift speed and the normal driving speed of the truck. The probability distribution of is as follows:

Among them, Lognorm(x; μ ₁ , σ ₁ ) is the probability density function of log-normal distribution, which is used to fit the velocity data of data drift; Norm(x; μ ₂ , σ ₂ ) is the probability density of normal distribution function, which is used to fit the speed data of the normal running of the truck, and uses the maximum likelihood method to estimate the parameters ω ₁ , ω ₂ , μ ₁ , μ ₂ , σ ₁ and σ ₂ of the mixture distribution;

The velocity threshold corresponding to the lowest point between the two peaks of the mixture distribution is determined as the velocity threshold. If the speed of the truck at a location is less than the speed threshold, the location is identified as a parking spot, and the geographic coordinates of a truck parking location are represented by the average of the latitude and longitude of all GPS points at the parking location.

Preferably, the parking points of the trucks are sorted in ascending order of parking time, and the multi-level time threshold is determined by drawing a Lorentz curve of the parking time, including:

Sort all the parking points of the truck in ascending order of parking time, draw the Lorentz curve of the parking time, calculate the intersection of the tangent at the rightmost endpoint of the Lorentz curve and the x-axis, and determine the parking time of the truck corresponding to the intersection is a time threshold, for the parking point whose parking time is less than the time threshold, redraw the Lorentz curve and calculate the intersection of the tangent and the x-axis, determine the time threshold of the next level, and iteratively execute the above process until Lorenz When the curve is a straight line, the multi-level time threshold is obtained.

Preferably, according to the multi-level time threshold, the detour degree of the single travel path of the truck is measured, and the potential travel OD points are extracted from the parking points of the truck, including:

Calculate the top K shortest paths from the departure point to the destination of each trip on the road network, find the nth shortest path that is closest to the actual travel path of the truck, and measure the single trip of the truck according to the nth shortest path The circuitous degree of the path, based on the circuitous degree of the single trip path of the truck, dynamically adjusts the time threshold;

Select the maximum time threshold, identify the parking point with the parking time greater than the maximum time threshold as a potential travel OD point, divide the original trajectory into multiple sub-tracks according to the potential travel OD point, name them as first-level sub-tracks, and calculate each segment. The nth shortest path between the starting point and the destination of a first-level sub-track. If the length of a certain first-level sub-track is greater than the calculated nth shortest path, it means that this first-level sub-track is longer than a single travel path. More circuitous, including travel OD points with shorter parking time; then, select the next-level time threshold to identify the travel OD points contained in the circuitous first-level sub-trajectories, and divide the first-level sub-trajectories into multiple second-level sub-trajectories in one step. , and iterates the above process continuously until the sub-trajectories cannot be segmented, indicating that all potential travel endpoints are extracted.

Preferably, the temporary parking points in the potential travel OD points are eliminated, and the actual travel OD points of the delivery vehicle are extracted, including:

Use road network data to determine whether trucks stay on the road for a long time due to traffic congestion. If a potential travel OD point is located on the road, it indicates that the potential travel OD point is a temporary parking point and needs to be eliminated; The point of interest data determines whether the truck is loading and unloading in the freight company. If the identified potential travel OD point is not located in the freight company, it indicates that the potential travel OD point is a temporary parking point and needs to be eliminated; otherwise, the potential travel OD point is real OD point of travel;

After extracting the actual travel OD points of the truck from the trajectory data, combined with the GPS data to extract the travel path of the truck, and calculate the travel-related indicators.

It can be seen from the technical solutions provided by the above embodiments of the present invention that the present invention proposes a method for dynamic identification of OD points of truck travel, which is applicable to all cities in the country. The method is highly transferable, low in complexity and easy to implement.

Additional aspects and advantages of the present invention will be set forth in part in the following description, which will be apparent from the following description, or may be learned by practice of the present invention.

Description of drawings

In order to illustrate the technical solutions of the embodiments of the present invention more clearly, the following briefly introduces the accompanying drawings used in the description of the embodiments. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can also be obtained from these drawings without any creative effort.

Fig. 1 is a processing flow chart of a method for extracting the OD of truck travel in a city from trajectory data provided by an embodiment of the present invention;

2 is a schematic diagram of determining a speed threshold according to an embodiment of the present invention;

3 is a schematic diagram of a truck parking spot identification according to an embodiment of the present invention;

4 is a schematic diagram of a multi-level time threshold determination provided by an embodiment of the present invention;

5 is a schematic diagram of determining the nth shortest path according to an embodiment of the present invention;

6 is a schematic diagram of extracting potential travel endpoints from truck parking points according to an embodiment of the present invention;

FIG. 7 is a schematic diagram of removing a temporary parking spot according to an embodiment of the present invention.

Detailed ways

Embodiments of the present invention are described in detail below, examples of which are illustrated in the accompanying drawings, wherein the same or similar reference numerals refer to the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present invention, but not to be construed as a limitation of the present invention.

It will be understood by those skilled in the art that the singular forms "a", "an", "the" and "the" as used herein can include the plural forms as well, unless expressly stated otherwise. It should be further understood that the word "comprising" used in the description of the present invention refers to the presence of stated features, integers, steps, operations, elements and/or components, but does not exclude the presence or addition of one or more other features, Integers, steps, operations, elements, components and/or groups thereof. It will be understood that when we refer to an element as being "connected" or "coupled" to another element, it can be directly connected or coupled to the other element or intervening elements may also be present. Furthermore, "connected" or "coupled" as used herein may include wirelessly connected or coupled. As used herein, the term "and/or" includes any and all combinations of one or more of the associated listed items.

It will be understood by those skilled in the art that, unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. It should also be understood that terms such as those defined in general dictionaries should be understood to have meanings consistent with their meanings in the context of the prior art and, unless defined as herein, are not to be taken in an idealized or overly formal sense. explain.

In order to facilitate the understanding of the embodiments of the present invention, the following will take several specific embodiments as examples for further explanation and description in conjunction with the accompanying drawings, and each embodiment does not constitute a limitation to the embodiments of the present invention.

The embodiment of the present invention extracts the OD of truck travel in a city from large-scale trajectory data, which mainly includes: determining a speed threshold suitable for a certain city according to the distribution of the speed of the truck, identifying the parking point from the original trajectory of the truck; The distribution of the stay time at the station determines multiple time thresholds, and measures the detour degree of the single trip path of the truck; based on the detour degree of the single trip path, the time threshold of the appropriate level is dynamically selected to identify the potential trip OD from all parking points Temporary parking points are eliminated from potential travel OD points using urban POI data and road network data, and then all real travel OD points are identified.

The processing flow chart of a method for extracting the OD of a truck trip in a city from trajectory data provided by an embodiment of the present invention is shown in FIG. 1 , and includes the following processing steps:

Step S10: Determine the speed threshold of the truck in the city, and identify the parking point from the truck track.

2 is a schematic diagram of determining a speed threshold provided by an embodiment of the present invention. For the GPS (Global Positioning System) track of each truck, the average speed of two consecutive GPS points in the GPS track is calculated respectively to obtain a city The distribution of the average speed of all trucks in the . The distribution of the average speed of the truck is the mixed distribution of the data drift speed and the normal running speed of the truck, and the average speed distribution is obtained by fitting the mixed distribution of formula (1).

The data drift speed refers to the possible deviation of the positioning of the GPS device, which will cause the GPS point of the stationary vehicle to drift, which is reflected in the data that the average speed of two consecutive GPS points is not 0. Therefore, the present invention distinguishes the data drift speed and the normal running speed of the truck by setting a speed threshold, thereby identifying the real parking point of the truck. If the average speed of two consecutive GPS points is less than the set speed threshold, the truck is stationary and a parking point can be identified.

The probability distribution of the mixture distribution is as follows:

Among them, Lognorm(x; μ ₁ , σ ₁ ) is the probability density function of log-normal distribution, which is mainly used to fit the velocity data of data drift; Norm(x; μ ₂ , σ ₂ ) is the probability of normal distribution The density function is mainly used to fit the speed data of the normal driving of the truck. The parameters ω ₁ , ω ₂ , μ ₁ , μ ₂ , σ ₁ and σ ₂ of the mixture distribution are estimated using the maximum likelihood method.

FIG. 3 is a schematic diagram of identifying a truck parking point according to an embodiment of the present invention, and a speed value corresponding to a saddle point of a mixed distribution (ie, the lowest point between two peaks in FIG. 3 ) is determined as a speed threshold. If the speed of the truck at a location is less than a determined speed threshold, the location is identified as a parking spot. The geographic coordinates of a truck parking spot are represented by the average of the latitude and longitude of all GPS points at that parking location.

Step S20: Sort the parking points of the trucks in ascending order of the parking time, and determine the multi-level time threshold by drawing the Lorentz curve of the parking time.

FIG. 4 is a schematic diagram of determining a multi-level time threshold according to an embodiment of the present invention, and the method uses a non-parametric iterative method to determine the multi-level time threshold. First, sort the parking points of the trucks in ascending order of the parking time, and draw the Lorentz curve of the parking time; then, calculate the intersection of the tangent at the rightmost endpoint of the Lorentz curve and the x-axis, and the intersection point corresponds to the parking time of the truck is determined as a time threshold, as shown in Fig. 4a; then, for parking points whose parking time is less than this time threshold, the time threshold for the next level is determined by redrawing the Lorentz curve and calculating the intersection of the tangent and the x-axis , as shown in Fig. 4b; the process iterates until the Lorentz curve is a straight line, as shown in Fig. 4h. After the iterative process is over, multi-level time thresholds can be obtained, which are used to identify potential travel OD points in step S30.

In the process of identifying potential travel OD points, the time threshold needs to be dynamically adjusted. The circuitous degree of a single trip path of a truck is the benchmark for the dynamic adjustment of the time threshold. In order to measure the circuitous degree of a single trip path of a truck, the OD points of some trucks are first extracted from the original GPS data using satellite images and urban POI as a sample data set. The OD points in the sample data set of the actual trip of the truck are manually extracted from the GPS data using satellite images and urban POIs, and are used as sample data to determine the algorithm parameters. These manually extracted OD points are a small part of the real travel OD points extracted in step S40 or can be understood as a subset. Locations associated with truck activity often have significant architectural features that can be identified from satellite imagery, so a small subset of truck OD points can be extracted from GPS data using manual methods. However, the geographic features of most of the truck OD points are not obvious, and the manual method is time-consuming, so it is not suitable for large-scale GPS data. This is also the actual background that the present invention takes into account.

Then, calculate the top K shortest paths from the starting point to the destination of each trip on the road network; then, find the nth (n≤K) shortest path closest to the actual travel path of the truck, which is used to measure the truck The circuitous degree of a single trip path. FIG. 5 is a schematic diagram of determining the nth shortest path according to an embodiment of the present invention.

Step S30: According to the multi-level time threshold and the nth shortest path, a potential travel OD point is extracted from the truck parking point.

FIG. 6 is a schematic diagram of extracting potential travel endpoints from truck parking points according to an embodiment of the present invention. The present invention uses the time threshold dynamic adjustment method to extract potential travel OD points from the parking points identified in step S10. First, select the maximum time threshold determined in step S20, identify the parking points whose parking time is greater than this time threshold as potential travel OD points, and divide the original trajectory into multiple sub-trajectories according to these travel endpoints, which are named as first-level sub-trajectories. trajectories, as shown in the second layer of Figure 6; then, calculate the nth shortest path between the starting point and the destination of each first-level sub-trajectory. If the length of a certain first-level sub-trajectory is greater than the calculated nth shortest path, it indicates that this first-level sub-trajectory is more circuitous than a single travel path, that is, it may contain travel OD points with shorter parking time; then, select the following The first-level time threshold identifies the trip OD points contained in the circuitous first-level sub-trajectories, and divides the first-level sub-trajectories into multiple second-level sub-trajectories in one step, as shown in the third layer of Figure 6; the above process continues to iterate until the sub-trajectories When the trajectory cannot be segmented, it indicates that all potential travel endpoints are extracted, as shown in the fourth layer of Figure 6.

Step S40: Eliminate the temporary parking points in the potential travel OD points, and extract the real travel OD points.

FIG. 7 is a schematic diagram of removing a temporary parking spot according to an embodiment of the present invention. The potential travel endpoints identified in step S30 may include long-term temporary parking points, such as long-term traffic congestion points and driver rest points, and these temporary parking points need to be eliminated to improve the accuracy of the method. First, use road network data to determine whether trucks are staying on the road for long periods of time due to traffic congestion. If a potential travel OD point is located on the road, it indicates that the potential travel OD point is a temporary parking point and needs to be eliminated, as shown in Figure 7a. Then, use point-of-interest data related to freight in the city to determine whether the truck is loading and unloading in the freight enterprise. If the identified potential travel OD point is not located in the freight enterprise, it indicates that the potential travel OD point is a temporary parking point and needs to be eliminated, as shown in Figure 7b; otherwise, the potential travel OD point is a real travel OD point, as shown in Figure 7c shown.

After extracting the actual travel OD points of the truck from the trajectory data, combined with the GPS data, the travel path of the truck can be extracted, and travel-related indicators can be calculated, such as travel distance, travel time, loading and unloading time, etc.

Table 1 shows a comparison of the method of the present invention with existing methods. The method accuracy M _acc is calculated as follows:

M _acc =NA/(NA+NM+NU) (2)

NA represents the number of accurately identified trip OD points, NM represents the number of incorrectly identified trip OD points, and NU represents the number of unidentified trip OD points. The results show that the accuracy of the method proposed by the present invention is significantly higher than that of the existing technology.

To sum up, the embodiment of the present invention proposes a data-driven method for determining a speed threshold, which is more accurate and objective, and has universality. Greatly reduces the possibility of parking spots being misidentified.

The invention proposes a data-driven multi-level time threshold determination method, which is accurate, objective and universal. Avoid temporary parking spots being mistakenly identified as parking spots, and improve the accuracy of the method.

The present invention proposes a method for processing temporary parking points by utilizing widely available urban interest point data and road network data, and improves the accuracy of the method.

The invention proposes a dynamic identification method for the OD point of truck travel, which can be applied to all cities in the country. The method is highly transferable, low in complexity and easy to implement.

Table 1 The method of the present invention is compared with the accuracy rate of the prior art

Those of ordinary skill in the art can understand that the accompanying drawing is only a schematic diagram of an embodiment, and the modules or processes in the accompanying drawing are not necessarily necessary to implement the present invention.

From the description of the above embodiments, those skilled in the art can clearly understand that the present invention can be implemented by means of software plus a necessary general hardware platform. Based on this understanding, the technical solutions of the present invention can be embodied in the form of software products in essence or the parts that make contributions to the prior art. The computer software products can be stored in storage media, such as ROM/RAM, magnetic disks, etc. , CD, etc., including several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the methods described in various embodiments or some parts of the embodiments of the present invention.

Each embodiment in this specification is described in a progressive manner, and the same and similar parts between the various embodiments may be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the apparatus or system embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and reference may be made to some descriptions of the method embodiments for related parts. The device and system embodiments described above are only illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, It can be located in one place, or it can be distributed over multiple network elements. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution in this embodiment. Those of ordinary skill in the art can understand and implement it without creative effort.

The above description is only a preferred embodiment of the present invention, but the protection scope of the present invention is not limited to this. Substitutions should be covered within the protection scope of the present invention. Therefore, the protection scope of the present invention should be subject to the protection scope of the claims.

Claims (5)

1. The method for extracting the urban truck trip OD from the trajectory data is characterized by comprising the following steps:

determining a speed threshold of a truck in the city, and identifying a parking point from a track of the truck according to the speed threshold;

sequencing the parking points of the truck according to the ascending sequence of the parking time, and determining a multi-stage time threshold value by drawing a Lorentz curve of the parking time;

measuring the roundabout degree of a single trip path of the truck according to the multi-stage time threshold, and extracting potential trip OD points from truck parking points;

and eliminating temporary parking points in the potential travel OD points, and extracting the real travel OD points of the truck.

2. The method of claim 1, wherein the sorting of the stops of the trucks in ascending order of stop time, and the determining the multi-level time threshold by plotting a Lorentzian curve of the stop time, comprises:

respectively calculating the average speeds of two continuous GPS points in the GPS tracks of all trucks in the city to obtain the distribution of the average speeds of all trucks, wherein the distribution of the average speeds of the trucks is the mixed distribution of data drift speed and normal running speed of the trucks, and the probability distribution of the mixed distribution is as follows:

wherein, Lognorm (x; mu)₁，σ₁) The probability density function is lognormal distribution and is used for fitting the speed data of data drifting; norm (x; mu)₂，σ₂) Is a normally distributed probability density function which is used for fitting the speed data of normal running of the truck and estimating a parameter omega of mixed distribution by utilizing a maximum likelihood method₁，ω₂，μ₁，μ₂，σ₁And σ₂；

A speed value corresponding to a lowest point between two peaks of the mixing profile is determined as the speed threshold. If the speed of the truck at a location is less than the speed threshold, the location is identified as a stop, and the geographic coordinates of a truck stop are represented by the average of the longitude and latitude of all GPS points at the stop.

3. The method of claim 1, wherein the sorting of the stops of the trucks in ascending order of stop time, and the determining the multi-level time threshold by plotting a Lorentzian curve of the stop time, comprises:

sequencing all parking points of the truck according to the ascending sequence of the parking time, drawing a Lorentz curve of the parking time, calculating the intersection point of a tangent line at the rightmost end point of the Lorentz curve and an x axis, determining the parking time of the truck corresponding to the intersection point as a time threshold, redrawing the Lorentz curve and calculating the intersection point of the tangent line and the x axis for the parking point with the parking time less than the time threshold, determining the time threshold of the next level, and continuously and iteratively executing the processing until the Lorentz curve is a straight line to obtain a multi-level time threshold.

4. The method according to claim 3, wherein said extracting potential travel OD points from truck stop points according to said measure of detour of single travel path of truck by said multi-stage time threshold comprises:

calculating the first K shortest paths from the starting place to the destination of each trip on a road network, finding out the nth shortest path closest to the actual trip path of the truck, measuring the roundabout degree of the single trip path of the truck according to the nth shortest path, and dynamically adjusting the time threshold by taking the roundabout degree of the single trip path of the truck as a reference;

selecting a maximum time threshold, identifying a parking point with parking time larger than the maximum time threshold as a potential travel OD point, dividing an original track into a plurality of sections of sub-tracks according to the potential travel OD point, naming the sub-track as a first-stage sub-track, calculating an nth shortest path between a departure place and a destination of each section of the first-stage sub-track, and if the length of a certain section of the first-stage sub-track is larger than the calculated nth shortest path, indicating that the section of the first-stage sub-track is roundabout more than a single travel path and comprises the travel OD point with short parking time; and then, selecting a next-stage time threshold value to identify travel OD points contained in the roundabout first-stage sub-track, dividing the first-stage sub-track into a plurality of sections of second-stage sub-tracks in one step, and continuously iterating the processing process until the sub-tracks cannot be divided, thereby indicating that all potential travel end points are extracted.

5. The method according to claim 4, wherein the step of eliminating the temporary stop points in the potential travel OD points and extracting the real travel OD point of the truck comprises:

judging whether the truck stays on the road for a long time due to traffic jam or not by using road network data, and if a certain potential travel OD point is located on the road, indicating that the potential travel OD point is a temporary parking point and needs to be removed; judging whether the truck loads and unloads goods in a freight enterprise or not by using the interest point data related to the freight in the city, and if the identified potential travel OD point is not located in the freight enterprise, indicating that the potential travel OD point is a temporary parking point and needs to be removed; otherwise, the potential travel OD point is a real travel OD point;

after the real travel OD point of the truck is extracted from the track data, the travel path of the truck is extracted by combining the GPS data, and the relevant travel index is calculated.

Images